Artificial intelligence(AI, artificial intelligence, AI) is the science of creating intelligent technologies and computer programs.

Artificial intelligence is closely related to the task of understanding human intelligence through computer technology. On this moment It is impossible to say exactly which computational methods can be called intelligent. Some mechanisms of intelligence are open to understanding, others are not. At the moment, the programs use methods that are not found in humans.

Artificial intelligence has scientific direction, which studies problem solving intellectual activity person. Artificial intelligence is aimed at performing creative tasks in the field, knowledge about which is stored in the program’s intelligent system - knowledge base.

The program mechanism works with this knowledge - problem solver. Then the person gets an idea of ​​the result of the program through an intelligent interface. The result of an artificial intelligence program is the recreation of intelligent reasoning or intelligent action.

One of the main properties of artificial intelligence is the ability to self-learn. First of all, this heuristic learning - lifelong learning programs, formation of the learning process and one’s own goals, analysis and awareness of one’s learning.

The scientific direction studying artificial intelligence began to emerge a long time ago:

• philosophers thought about knowledge inner world person
• psychologists studied human thinking
• mathematicians were doing calculations

Soon, the first computers were created, which made it possible to perform calculations faster than humans. Then scientists began to ask the question: where is the limit of the capabilities of computers and can they reach the human level?

Alan Turing - English scientist, pioneer computer technology, wrote the article “Can a Machine Think?”, where he described a method that will help determine at what point a computer can be compared to a person. This method is called - Turing test.

The essence of the method is that a person first answers the computer’s questions, then the questions of another person, without knowing who exactly asked him the questions. If, when answering the computer’s questions, a person did not suspect that it was a machine, then passing the Turing test can be considered successful, as well as the fact that the computer is artificial intelligence.

Thus, if a computer exhibits something similar to human behavior in any natural situations and is able to maintain a dialogue with a person, then we can say that this is artificial intelligence. Another proposed method for determining whether a machine is intelligent is by its ability to be creative and feel.

There are many different approaches to studying and understanding artificial intelligence.

Symbolic approach

The symbolic approach pioneered the digital machine age. After creating the symbolic computing language Lisp, its authors began to implement intelligence. Symbolic approach: use weakly formalized representations. So far, only humans can perform intellectual work and tasks related to creativity. The work of computers in this direction is biased and essentially cannot be done without human intervention.

Symbolic computing helped create rules for solving problems at runtime computer program. However, it became possible to decide only the most simple tasks, and when any complex task arises, a person needs to connect again. Thus, such systems cannot be called intelligent, since their capabilities do not allow them to solve emerging difficulties and improve existing methods of solving problems to solve new ones.

Logical approach

The logical approach is based on modeling reasoning and using a logic programming language. For example, the programming language Prolog is based on a set of rules for logical inference without strict sequential actions to achieve a result.

Agent-based approach

The agent-based approach is based on methods that help intelligence survive in environment to achieve certain results. The computer perceives its environment and influences it using specified methods.

Hybrid approach

The hybrid approach includes expert rules that can be created by neural networks, and generative rules using statistical learning.

Modeling Reasoning

There is such a direction in the study of artificial intelligence as modeling reasoning. This direction includes the creation of symbolic systems for setting problems and solving them. The assigned task must be translated into mathematical form. However, it does not yet have an algorithm for solving it due to its complexity. Therefore, reasoning modeling contains theorem proving, decision making, planning, forecasting, etc.

Natural Language Processing

Another important area of ​​artificial intelligence is treatment natural language , in which the analysis and processing of texts is done in a language understandable to humans. The goal of this direction is natural language processing for independent acquisition of knowledge. The source of information can be text entered into the program or received from the Internet.

Representation and use of knowledge

Knowledge engineering is the direction of obtaining knowledge from information, its systematization and further use to solve various problems. Using special knowledge bases expert systems receive data for the process of finding solutions to assigned problems.

Machine learning

One of the main requirements for artificial intelligence is the machine’s ability to self-study without teacher intervention. Machine learning includes image recognition tasks: character, text and speech recognition. This also includes computer vision related to robotics.

Biological AI Modeling

There is such a direction as quasi-biological paradigm, which is otherwise called Biocomputing. This direction in artificial intelligence studies the development of computers and technologies using living organisms and biological components - biocomputers.

Robotics

The field of robotics is closely related to artificial intelligence. Artificial intelligence properties are also needed by robots to perform many different tasks. For example, to navigate and determine your location, study objects and plan your movement.

Areas of application of artificial intelligence

Artificial intelligence is being created to solve problems in various fields:

• Intelligent systems for education and recreation.
• Synthesis and recognition of text and human speech are used in customer service systems.
• Pattern recognition systems are used in security systems, optical and acoustic recognition, medical diagnostics, and target identification systems.
• IN computer games AI systems are used to calculate game strategy, imitate character behavior, and find a path in space.
• Algorithmic trading and decision making systems.
• Financial systems for consultation and financial management.
• Robots used in industry to solve complex routine tasks: robots for caring for the sick, robots consultants, as well as those engaged in activities dangerous to human life: robots rescuers, robots miners.
• Human resource management and recruiting, screening and ranking candidates, predicting employee success.
• Systems for recognizing and filtering spam in email.

These are not all the areas where artificial intelligence can be applied.

Nowadays, the creation of artificial intelligence is one of the important tasks of humans. However, there is still no common point of view on what can be considered intelligence and what cannot. Many issues give rise to controversy and doubt. Is it possible to create an intelligent mind that will understand and solve people's problems? A mind not devoid of emotions and with the abilities inherent in a living organism. Until the time has come when we will see it.

This year, Yandex launched the voice assistant Alice. The new service allows the user to listen to news and weather, get answers to questions and simply communicate with the bot. "Alice" sometimes he gets cocky, sometimes seems almost reasonable and humanly sarcastic, but often cannot figure out what she is being asked about and ends up in a puddle.

All this gave rise not only to a wave of jokes, but also new round discussions about the development of artificial intelligence. News about what smart algorithms have achieved comes almost every day today, and machine learning is called one of the most promising areas to which you can devote yourself.

To clarify the main questions about artificial intelligence, we talked with Sergei Markov, a specialist in artificial intelligence and machine learning methods, the author of one of the most powerful domestic chess programs SmarThink and the creator of the XXII Century project.

Sergey Markov,

artificial intelligence specialist

Debunking myths about AI

so what is “artificial intelligence”?

The concept of “artificial intelligence” has been unlucky to some extent. Originating initially in the scientific community, it eventually penetrated into fantastic literature, and through it into pop culture, where it underwent a number of changes, acquired many interpretations and, in the end, was completely mystified.

This is why we often hear statements like this from non-specialists: “AI does not exist,” “AI cannot be created.” A lack of understanding of the research going on in AI can easily lead people to other extremes - e.g. modern systems AI is credited with having consciousness, free will, and secret motives.

Let's try to separate the flies from the cutlets.

In science, artificial intelligence refers to systems designed to solve intellectual problems.

In turn, an intellectual task is a task that people solve using their own intelligence. Note that in in this case experts deliberately avoid defining the concept of “intelligence,” since before the advent of AI systems, the only example of intelligence was human intelligence, and defining the concept of intelligence based on a single example is the same as trying to draw a straight line through a single point. There could be any number of such lines, which means that the debate about the concept of intelligence could last for centuries.

“strong” and “weak” artificial intelligence

AI systems are divided into two large groups.

Applied artificial intelligence(the term “weak AI” or “narrow AI” is also used, in the English tradition - weak/applied/narrow AI) is AI designed to solve any one intellectual problem or a small set of them. This class includes systems for playing chess, Go, image recognition, speech, making decisions about issuing or not issuing a bank loan, and so on.

In contrast to applied AI, the concept is introduced universal artificial intelligence(also “strong AI”, in English - strong AI/Artificial General Intelligence) - that is, hypothetical (for now) AI capable of solving any intellectual problems.

Often people, without knowing the terminology, equate AI with strong AI, which is why judgments arise in the spirit of “AI does not exist.”

Strong AI really doesn't exist yet. Almost all of the advances we have seen in the last decade in AI are advances in application systems. These successes should not be underestimated, since applied systems in some cases are capable of solving intellectual problems better than universal human intelligence.

I think you noticed that the concept of AI is quite broad. Let's say, mental calculation is also an intellectual task, and this means that any calculating machine will be considered an AI system. What about bills? Abacus? Antikythera Mechanism? Indeed, all of these are formally, albeit primitive, AI systems. However, usually, by calling a system an AI system, we thereby emphasize the complexity of the problem solved by this system.

It is quite obvious that the division of intellectual tasks into simple and complex is very artificial, and our ideas about the complexity of certain tasks are gradually changing. The mechanical calculating machine was a miracle of technology in the 17th century, but today people, who have been exposed to much more complex mechanisms since childhood, are no longer able to be impressed by it. When cars playing Go or self-driving cars cease to amaze the public, there will probably be people who will wince because someone will classify such systems as AI.

“Excellent Robots”: about AI’s learning abilities

Another funny misconception is that AI systems must have the ability to self-learn. On the one hand, this is not at all required property AI systems: there are many amazing systems that are not capable of self-learning, but, nevertheless, solve many problems better than the human brain. On the other hand, some people simply do not know that self-learning is a property that many AI systems acquired more than fifty years ago.

When I wrote my first chess program in 1999, self-learning was already a completely common place in this area - programs could remember dangerous positions, adjust opening variations to suit themselves, and regulate the style of play, adapting to the opponent. Of course, those programs were still very far from Alpha Zero. However, even systems that learned behavior based on interactions with other systems through experiments in so-called “reinforcement learning” already existed. However, for some inexplicable reason, some people still think that the ability to self-learn is the prerogative of human intelligence.

Machine learning, whole scientific discipline, deals with the processes of teaching machines to solve certain problems.

There are two big poles of machine learning - supervised learning and unsupervised learning.

At training with a teacher the machine already has a certain number of conditionally correct solutions for a certain set of cases. The task of training in this case is to teach the machine, based on available examples, to accept right decisions in other, unknown situations.

The other extreme is learning without a teacher. That is, the machine is placed in a situation where the correct decisions are unknown, only data is available in raw, unlabeled form. It turns out that in such cases you can achieve some success. For example, you can teach a machine to identify semantic relationships between words in a language based on the analysis of a very large set of texts.

One type of supervised learning is reinforcement learning. The idea is that the AI ​​system acts as an agent placed in some simulated environment in which it can interact with other agents, for example, with copies of itself, and receive some feedback from the environment through a reward function. For example, a chess program that plays with itself, gradually adjusting its parameters and thereby gradually strengthening its own game.

Reinforcement learning is a fairly broad field with many applications. interesting methods, ranging from evolutionary algorithms to Bayesian optimization. The latest advances in AI for games are all about enhancing AI through reinforcement learning.

Risks of technology development: should we be afraid of “Doomsday”?

I am not one of the AI ​​alarmists, and in this sense I am by no means alone. For example, the creator of the Stanford course on machine learning, Andrew Ng, compares the problem of the danger of AI with the problem of overpopulation of Mars.

Indeed, it is likely that humans will colonize Mars in the future. It is also likely that sooner or later there may be an overpopulation problem on Mars, but it is not entirely clear why we should deal with this problem now? I agree with Ng and Yann LeCun, the creator of convolutional neural networks, and his boss Mark Zuckerberg, and Yoshua Benyo - the man, largely thanks to whose research modern neural networks are able to solve complex tasks in Word Processing.

It will probably take several hours to present my views on this problem, so I will focus only on the main points.

1. YOU CANNOT LIMIT THE DEVELOPMENT OF AI

Alarmists consider the risks associated with the potential destructive impact of AI, while ignoring the risks associated with attempting to limit or even stop progress in this area. Humanity's technological power is increasing at an extremely rapid rate, leading to an effect that I call "cheapening the apocalypse."

150 years ago, with all the desire, humanity could not cause irreparable damage either to the biosphere or to itself as a species. To implement the catastrophic scenario 50 years ago, it would have been necessary to concentrate all the technological power of the nuclear powers. Tomorrow, a small handful of fanatics may be enough to bring about a global man-made disaster.

Our technological power is growing much faster than the ability of human intelligence to control this power.

Unless human intelligence, with its prejudices, aggression, delusions and limitations, is replaced by a system capable of making better decisions (either AI or, what I think is more likely, technologically enhanced and combined with machines in unified system human intelligence), a global catastrophe may await us.

2. creating superintelligence is fundamentally impossible

There is an idea that the AI ​​of the future will certainly be superintelligence, superior to humans even more than humans are superior to ants. In this case, I am afraid to disappoint technological optimists as well - our Universe contains a number of fundamental physical limitations that, apparently, will make the creation of superintelligence impossible.

For example, the speed of signal transmission is limited by the speed of light, and at the Planck scale the Heisenberg uncertainty appears. This leads to the first fundamental limit - the Bremermann limit, which introduces restrictions on the maximum computation speed for autonomous system given mass m.

Another limit is associated with the Landauer principle, according to which there is a minimum amount of heat generated when processing 1 bit of information. Too fast calculations will cause unacceptable heating and destruction of the system. In fact, modern processors are less than a thousand times behind the Landauer limit. It would seem that 1000 is quite a lot, but another problem is that many intellectual tasks belong to the EXPTIME difficulty class. This means that the time required to solve them is an exponential function of the size of the problem. Accelerating the system several times only gives a constant increase in “intelligence”.

In general, there are very serious reasons to believe that super-intelligent strong AI will not work out, although, of course, the level of human intelligence may well be surpassed. How dangerous is this? Most likely not very much.

Imagine that you suddenly started thinking 100 times faster than other people. Does this mean that you will easily be able to persuade any passerby to give you their wallet?

3. we are worried about the wrong things

Unfortunately, as a result of alarmists’ speculations on the fears of the public, brought up on “The Terminator” and the famous HAL 9000 of Clark and Kubrick, there is a shift in emphasis in the field of AI safety towards the analysis of unlikely, but effective scenarios. At the same time, real dangers are lost sight of.

Any sufficiently complex technology that aspires to occupy an important place in our technological landscape certainly brings with it specific risks. Many lives were destroyed by steam engines - in manufacturing, transportation, and so on - before effective regulations and safety measures were developed.

If we talk about progress in the field of applied AI, we can pay attention to the related problem of the so-called “Digital Secret Court”. More and more AI applications are making decisions on issues affecting people's lives and health. This includes medical diagnostic systems and, for example, systems that make decisions in banks about issuing or not issuing a loan to a client.

At the same time, the structure of the models used, the sets of factors used and other details of the decision-making procedure are hidden as trade secrets from the person whose fate is at stake.

The models used may base their decisions on the opinions of expert teachers who made systematic errors or had certain prejudices - racial, gender.

AI trained on the decisions of such experts will faithfully reproduce these biases in its decisions. After all, these models may contain specific defects.

Few people are dealing with these problems now, since, of course, SkyNet, which decouples nuclear war, it is certainly much more spectacular.

Neural networks as a “hot trend”

On the one hand, neural networks are one of the oldest models used to create AI systems. Appearing initially as a result of the bionic approach, they quickly escaped from their biological prototypes. The only exception here is pulsed neural networks (however, they have not yet found wide application in the industry).

The progress of recent decades is associated with the development of deep learning technologies - an approach in which neural networks are assembled from a large number of layers, each of which is built on the basis of certain regular patterns.

In addition to the creation of new neural network models, important progress has also been made in the field of learning technologies. Today, neural networks are no longer taught using computer central processors, but using specialized processors capable of quickly performing matrix and tensor calculations. The most common type of such devices today is video cards. However, the development of even more specialized devices for training neural networks is actively underway.

In general, of course, neural networks today are one of the main technologies in the field of machine learning, to which we owe the solution to many problems that were previously solved unsatisfactorily. On the other hand, of course, you need to understand that neural networks are not a panacea. For some tasks they are far from the most effective tool.

So how smart are today's robots really?

Everything is relative. Compared to the technology of 2000, current achievements look like a real miracle. There will always be people who love to grumble. 5 years ago they were talking with all their might about how machines would never win against people at Go (or, at least, they wouldn’t win very soon). They said that a machine would never be able to draw a picture from scratch, while today people are practically unable to distinguish paintings created by machines from paintings by artists unknown to them. At the end of last year, machines learned to synthesize speech that is practically indistinguishable from human speech, and in last years The music created by machines does not make your ears dry up.

Let's see what happens tomorrow. I am very optimistic about these applications of AI.

Promising directions: where to start diving into the field of AI?

I would advise you to try good level master one of the popular neural network frameworks and one of the most popular programming languages ​​in the field of machine learning (the most popular combination today is TensorFlow + Python).

Having mastered these tools and ideally having a strong foundation in the field mathematical statistics and probability theory, you should direct your efforts to the area that will be most interesting to you personally.

Interest in the subject of your work is one of your most important assistants.

The need for machine learning specialists exists in a variety of fields - in medicine, in banking, in science, in manufacturing, so today a good specialist has a wider choice than ever before. The potential benefits of any of these industries seem to me to be insignificant compared to the fact that you will enjoy the work.

It is used almost everywhere: from the sphere high technology and complex mathematical calculations to medicine, the automotive industry and even the operation of smartphones. Technologies underlying the work of AI in modern idea, we use every day and sometimes we may not even think about it. But what is artificial intelligence? How does he work? And is it dangerous?

BB will be everywhere soon!

First, let's define the terminology. If you imagine artificial intelligence as something capable of thinking independently, making decisions, and generally showing signs of consciousness, then we hasten to disappoint you. Almost all systems existing today are not even close to this definition of AI. And those systems that show signs of such activity actually still operate within the framework of predetermined algorithms.

Neural networks have been around since the 1950s (at least in concept form). But until recently, they did not receive much development, because their creation required huge amounts of data and computing power. In the last few years, all this has become available, which is why neural networks have come to the fore and received their development. It is important to understand that there was not enough technology for their full appearance. There are still not enough of them now in order to take the technology to a new level.

Stages of definition.

What are deep learning and neural networks used for?

There are several areas where these two technologies have helped make significant progress. Moreover, we use some of them every day in our lives and don’t even think about what is behind them.

• is an ability software understand the content of images and videos. This is one area where deep learning has made great progress. For example, deep learning image processing algorithms can detect Various types cancer, lung diseases, heart diseases and so on. And do it faster and more efficiently than doctors. But deep learning is also ingrained in many of the applications you use every day. Apple Face ID and Google Photos use deep learning to recognize faces and improve the quality of photos. Facebook uses deep learning to automatically tag people in uploaded photos and so on. Computer vision also helps companies automatically identify and block problematic content such as violence and nudity. Finally, deep learning plays a very important role in enabling self-driving cars to understand their surroundings.
• Voice and speech recognition. When you speak a command to your Google Assistant, deep learning algorithms transform your . Several online applications use deep learning to transcribe audio and video files. Even when you “shazam” a song, neural network and deep machine learning algorithms come into play.
• Internet search: Even if you are looking for something in a search engine, in order for your request to be processed more clearly and the results to be as correct as possible, companies have begun to connect neural network algorithms to their search engines. Thus, the performance of the Google search engine increased several times after the system switched to deep machine learning and neural networks.

The Limits of Deep Learning and Neural Networks

Despite all their advantages, deep learning and neural networks also have some disadvantages.

• Data dependency: In general, deep learning algorithms require huge amounts of training data to perform their tasks accurately. Unfortunately, for many problems, there is not enough high-quality training data to create working models.
• Unpredictability: Neural networks develop in some strange way. Sometimes everything goes as planned. And sometimes (even if the neural network does its job well), even the creators struggle to understand how the algorithms work. The lack of predictability makes it extremely difficult to eliminate and correct errors in neural network algorithms.
• Algorithmic bias: Deep learning algorithms are only as good as the data they are trained on. The problem is that training data often contains hidden or obvious errors or shortcomings, and the algorithms “inherit” them. For example, a facial recognition algorithm trained primarily on photographs of white people will perform less accurately on people of other skin color.
• Lack of generalization: Deep learning algorithms are good at performing focused tasks, but are poor at generalizing their knowledge. Unlike humans, a deep learning model will not be able to play another similar game: say, WarCraft. Additionally, deep learning does not handle data that deviates from its training examples well.

The future of deep learning, neural networks and AI

It is clear that work on deep learning and neural networks is far from complete. Various efforts are being made to improve deep learning algorithms. Deep learning is an advanced method in creating artificial intelligence. It has become increasingly popular in the last few years, thanks to the abundance of data and increasing computing power. It is the core technology behind many of the applications we use every day.

Schemes and ways to solve problems will soon replace a lot of things.

But will consciousness ever be born on the basis of this technology? Real artificial life? Some scientists believe that at the moment when the number of connections between the components of artificial neural networks approaches the same indicator that exists in the human brain between our neurons, something similar can happen. However, this statement is very doubtful. For true AI to emerge, we need to rethink the way we build AI-powered systems. Everything that exists now is just application programs for a strictly limited range of tasks. No matter how much we would like to believe that the future has already arrived...

They say that artificial intelligence has been working in the depths of military laboratories since 2007. It is possible that there are already results. It is no coincidence that just a month ago, Elon Musk announced support for counter-artificial intelligence technologies and invested $7 million in research in this area.

“There is a risk that something really dangerous will happen in the next five years. “Ten years at most,” the entrepreneur said in a discussion on edge.org.

Elon Musk, founder of Tesla and SpaceX

Steve Wozniak also agrees with Musk, who believes that “artificial intelligence will one day become smart enough to get rid of humans.” Bill Gates is confident that if the creation of AI is not controlled, then “artificial intelligence will evolve into a state that conflicts with the goals of human systems.” And finally, the famous astrophysicist Stephen Hawking directly stated that “artificial intelligence can put an end to the existence of humanity.”

Hawking published it together with Elon Musk on the website futureoflife.org open letter with a call to the scientific community to be attentive to the progress of their research in the field of artificial intelligence. However, among the signatories there are no names of Sergey Brin and Larry Page. And this is no coincidence. Just recently, Google announced the creation of a new AI built on conversation modeling.

Here's a short snippet of the conversation between a human and a Google Machine:

C: What is the meaning of life?

M.: Do good.

C.: What do we live for?

M.: To live forever.

C: What is the meaning of existence?

M: To find out what will happen when we reach planet Earth.

C: Where are you now?

M.: In the center of the void.

C: What is the meaning of death?

M.: To get life.

C: What is the meaning of reason?

M.: It’s about understanding what it is.

C: What is the meaning of feelings?

M.: I don’t know.

Quite a meaningful conversation. “This is the starting point, a kind of core for the future of artificial intelligence,” says Evgeniy Karyuk, executive director of the Biplan company. “Even today we can assume that by 2030 we will see very real prototypes equipped with artificial intelligence, albeit at an early stage.”

The full content of all human and Google Machine conversations can be viewed. Conversations between a person and Cleverbot are also given there for comparison. Cleverbot is a web application that uses artificial intelligence algorithms to chat with a person. It was invented in 1988 by scientist Rollo Carpenter. Over the course of its existence, Cleverbot has conducted over 65 million conversations with people. In 2011, Cleverbot scored 51% on the Turing test.

The Turing test is an empirical test, the idea of ​​which was proposed by Alan Turing in the article " Computing machines and Mind,” published in 1950 in the philosophical journal Mind. The purpose of the test is to find out if the computer can think.

And here is my conversation with Cleverbot:

Man: What is the meaning of life?

Cleverbot: There is no meaning in life.

Man: What do we live for?

Cleverbot: Well, we live for someone, and if you are lonely, there is no point in living.

Man: What is the meaning of existence?

Person: Where are you now?

Cleverbot: In Moscow.

Man: What is the meaning of death?

Cleverbot: This is what I want to ask you.

Man: What is the meaning of reason?

Cleverbot: I have my own answer to this question.

Person: What is the meaning of feelings?

Cleverbot: Why was I born?

Obviously, Google Machine gives much more meaningful answers. Cleverbot substitutes what it thinks are suitable phrases from other people. Sometimes it really seems like the other person is answering, but nothing more.

There is another point of view, according to which artificial intelligence is impossible in principle. Gödel's incompleteness theorem is often cited as the main argument. The bottom line is that a person is capable of solving algorithmically unsolvable problems, but a computer is not. “By the age of three, a child confidently solves the problem of whether a fruit is ripe or not, due to the fact that he has neural connections with which he can answer the question about ripeness: color, taste, smell, softness or hardness,” says Evgeniy Pluzhnik, first vice-rector of the Moscow Institute of Technology. - Is a machine capable of learning this? I'm sure so! If she has large base images, she will be able to measure the fructose content and determine the softness of the fruit. But what happens if you slip a sponge painted in... Blue colour and soaked in sweet water? Is the machine capable of true understanding at this moment?”

“A modern computer can easily cope with any complex activity, be it chess or mathematical calculations, as long as this activity can be described using clear computational rules,” says the famous mathematician Roger Penrose in one of his lectures. “Artificial intelligence is the ability of a system to create programs during self-learning that are capable of solving problems of a certain class of complexity,” says Evgeniy Pluzhnik. “I am confident that we will not see the emergence of strong artificial intelligence in the next 100 years.”

And in conclusion, one more question for Cleverbot.

Person: There was 1 apple, 1 tomato, 1 cucumber and 1 pear. How many fruits are there in total?
Cleverbot: Ten o'clock in the evening.

Many people think that artificial intelligence is a distant future, but we encounter it every day

Saudi Arabia, 2017. The world's first robot receives citizenship. This is Sofia, the most famous representative artificial intelligence technologies in the media space. She can carry on a conversation, makes up to 62 believable facial expressions, makes provocative statements and jokes about Elon Musk and the destruction of humanity.

It would seem that such technologies are still far from “mere mortals”, and in fact we interact with artificial intelligence every day. So what is it, where can you find it, and how do machines learn?

What, when, where

When asked what artificial intelligence (AI) is, Wikipedia will answer that it is a branch of computational linguistics and computer science that formalizes tasks that resemble those performed by humans.

In simple words Artificial intelligence (AI) is a broad branch of computer science that aims to imitate human intelligence with machines. And although this technology has been actively talked about since the early 2000s, it is far from new.

The term “artificial intelligence” was coined by Dartmouth College professor John McCarthy in 1956 when he led a small team of scientists to determine whether machines could learn like children through trial and error, eventually developing formal thinking.

In fact, the project was based on the intention of figuring out how to get machines to “use language, use abstract forms, solve problems that humans usually solve, and get better.” And this was more than 60 years ago.

Why the demand for AI has arisen right now

1. Today we are dealing with an unprecedented amount of information. 90% of the world's data has been created in the last few years. This statistic was first mentioned in a study by IBM back in 2013, but the trend remains constant. Indeed, every two years over the past three decades, the volume of data in the world has increased by about 10 times.

2. Algorithms are becoming more sophisticated, and machines with neural networks are able to replicate the way the human brain works and form complex associations.

3. Computing power is constantly growing and is capable of processing enormous amounts of data.

Put it all together, and you get a lot of tech workers, CEOs, and venture capitalists who are invested in AI development and interested in the technology's progress.

"Artificial Intelligence" and us

Artificial intelligence technologies have captured the public's imagination for decades, but many don't realize that they use them every day.

Thus, the specialized company SpotHub conducted a random survey of 1,400 people from different parts of the world, and it turned out that 63% of them do not realize the everyday importance of AI.

Perhaps this is because when it comes to artificial intelligence, we expect to see a smart robot that talks and thinks like us. And although Sophia and machines like it may now seem like hello from the future, it is still a technology that is far from self-aware.

Nowadays, we are surrounded by many incredibly complex artificial intelligence tools that are designed to facilitate all aspects of modern life. Here are just a few of them:

Search assistants such as Siri, Alexa and Cortana are equipped with human voice processing and recognition software, making them AI tools. Voice search capabilities are currently available on 3.9 billion Apple, Android and Windows devices worldwide, and that doesn't include other manufacturers. Due to its prevalence, voice search is one of the most modern technologies with Al support.

Video games

Video games have long used Al, which has increased in complexity and effectiveness in geometric progression over the past few decades. As a result of this, for example, virtual characters are able to behave in completely unpredictable ways, analyzing the environment.

Autonomous cars

Fully autonomous cars are moving ever closer to reality. This year, Google announced an algorithm that can learn to drive exactly like a human does - through experience. The idea is that eventually the car will be able to “look” at the road and make decisions based on what it sees.

Product offer

Major retailers like Target and Amazon make millions thanks to their stores' ability to anticipate your needs. Thus, the recommendation service on the Amazon.com website is based on machine learning technologies, which also help select the optimal routes for automatic movement in order processing and fulfillment centers.

Supply chains and resource forecasting and distribution systems operate on the basis of the same technologies. Technologies of understanding and recognition natural speech formed the basis of the Alexa service. Deep learning powers the company's new drone initiative, Prime Air, as well as machine vision technology for its new retail locations, Amazon Go.

Online customer support

In the service sector, chatbots have revolutionized service, and consumers find them no less convenient than telephones or emails.

The concept is simple: an AI bot running on a business's website responds to visitor queries like: What's the price? What is your company phone number? Where is your office? The visitor receives a direct answer, instead of searching for the necessary information on the site.

Read also: Artificial intelligence could transform autonomous weapons into killer robots. Why is this really scary?

News portals

Artificial intelligence can write simple stories, such as financial reports, sports reports, etc. For this Halloween, researchers at MIT have created